Machine-Translation Inspired Reordering As Preprocessing for Cross-Lingual Sentiment Analysis
Total Page:16
File Type:pdf, Size:1020Kb
Load more
Recommended publications
-
Student Research Workshop Associated with RANLP 2011, Pages 1–8, Hissar, Bulgaria, 13 September 2011
RANLPStud 2011 Proceedings of the Student Research Workshop associated with The 8th International Conference on Recent Advances in Natural Language Processing (RANLP 2011) 13 September, 2011 Hissar, Bulgaria STUDENT RESEARCH WORKSHOP ASSOCIATED WITH THE INTERNATIONAL CONFERENCE RECENT ADVANCES IN NATURAL LANGUAGE PROCESSING’2011 PROCEEDINGS Hissar, Bulgaria 13 September 2011 ISBN 978-954-452-016-8 Designed and Printed by INCOMA Ltd. Shoumen, BULGARIA ii Preface The Recent Advances in Natural Language Processing (RANLP) conference, already in its eight year and ranked among the most influential NLP conferences, has always been a meeting venue for scientists coming from all over the world. Since 2009, we decided to give arena to the younger and less experienced members of the NLP community to share their results with an international audience. For this reason, further to the first successful and highly competitive Student Research Workshop associated with the conference RANLP 2009, we are pleased to announce the second edition of the workshop which is held during the main RANLP 2011 conference days on 13 September 2011. The aim of the workshop is to provide an excellent opportunity for students at all levels (Bachelor, Master, and Ph.D.) to present their work in progress or completed projects to an international research audience and receive feedback from senior researchers. We have received 31 high quality submissions, among which 6 papers have been accepted as regular oral papers, and 18 as posters. Each submission has been reviewed by -
ALW2), Pages 1–10 Brussels, Belgium, October 31, 2018
EMNLP 2018 Second Workshop on Abusive Language Online Proceedings of the Workshop, co-located with EMNLP 2018 October 31, 2018 Brussels, Belgium Sponsors Primary Sponsor Platinum Sponsors Gold Sponsors Silver Sponsors Bronze Sponsors ii c 2018 The Association for Computational Linguistics Order copies of this and other ACL proceedings from: Association for Computational Linguistics (ACL) 209 N. Eighth Street Stroudsburg, PA 18360 USA Tel: +1-570-476-8006 Fax: +1-570-476-0860 [email protected] ISBN 978-1-948087-68-1 iii Introduction Interaction amongst users on social networking platforms can enable constructive and insightful conversations and civic participation; however, on many sites that encourage user interaction, verbal abuse has become commonplace. Abusive behavior such as cyberbullying, hate speech, and scapegoating can poison the social climates within online communities. The last few years have seen a surge in such abusive online behavior, leaving governments, social media platforms, and individuals struggling to deal with the consequences. As a field that works directly with computational analysis of language, the NLP community is uniquely positioned to address the difficult problem of abusive language online; encouraging collaborative and innovate work in this area is the goal of this workshop. The first year of the workshop saw 14 papers presented in a day-long program including interdisciplinary panels and active discussion. In this second edition, we have aimed to build on the success of the first year, maintaining a focus on computationally detecting abusive language and encouraging interdisciplinary work. Reflecting the growing research focus on this topic, the number of submissions received more than doubled from 22 in last year’s edition of the workshop to 48 this year. -
Using Morphemes from Agglutinative Languages Like Quechua and Finnish to Aid in Low-Resource Translation
Using Morphemes from Agglutinative Languages like Quechua and Finnish to Aid in Low-Resource Translation John E. Ortega [email protected] Dept. de Llenguatges i Sistemes Informatics, Universitat d’Alacant, E-03071, Alacant, Spain Krishnan Pillaipakkamnatt [email protected] Department of Computer Science, Hofstra University, Hempstead, NY 11549, USA Abstract Quechua is a low-resource language spoken by nearly 9 million persons in South America (Hintz and Hintz, 2017). Yet, in recent times there are few published accounts of successful adaptations of machine translation systems for low-resource languages like Quechua. In some cases, machine translations from Quechua to Spanish are inadequate due to error in alignment. We attempt to improve previous alignment techniques by aligning two languages that are simi- lar due to agglutination: Quechua and Finnish. Our novel technique allows us to add rules that improve alignment for the prediction algorithm used in common machine translation systems. 1 Introduction The NP-complete problem of translating natural languages as they are spoken by humans to machine readable text is a complex problem; yet, is partially solvable due to the accuracy of machine language translations when compared to human translations (Kleinberg and Tardos, 2005). Statistical machine translation (SMT) systems such as Moses 1, require that an algo- rithm be combined with enough parallel corpora, text from distinct languages that can be com- pared sentence by sentence, to build phrase translation tables from language models. For many European languages, the translation task of bringing words together in a sequential sentence- by-sentence format for modeling, known as word alignment, is not hard due to the abundance of parallel corpora in large data sets such as Europarl 2. -
A Massively Parallel Corpus: the Bible in 100 Languages
Lang Resources & Evaluation DOI 10.1007/s10579-014-9287-y ORIGINAL PAPER A massively parallel corpus: the Bible in 100 languages Christos Christodouloupoulos • Mark Steedman Ó The Author(s) 2014. This article is published with open access at Springerlink.com Abstract We describe the creation of a massively parallel corpus based on 100 translations of the Bible. We discuss some of the difficulties in acquiring and processing the raw material as well as the potential of the Bible as a corpus for natural language processing. Finally we present a statistical analysis of the corpora collected and a detailed comparison between the English translation and other English corpora. Keywords Parallel corpus Á Multilingual corpus Á Comparative corpus linguistics 1 Introduction Parallel corpora are a valuable resource for linguistic research and natural language processing (NLP) applications. One of the main uses of the latter kind is as training material for statistical machine translation (SMT), where large amounts of aligned data are standardly used to learn word alignment models between the lexica of two languages (for example, in the Giza?? system of Och and Ney 2003). Another interesting use of parallel corpora in NLP is projected learning of linguistic structure. In this approach, supervised data from a resource-rich language is used to guide the unsupervised learning algorithm in a target language. Although there are some techniques that do not require parallel texts (e.g. Cohen et al. 2011), the most successful models use sentence-aligned corpora (Yarowsky and Ngai 2001; Das and Petrov 2011). C. Christodouloupoulos (&) Department of Computer Science, UIUC, 201 N. -
A Corpus-Based Study of Unaccusative Verbs and Auxiliary Selection
To be or not to be: A corpus-based study of unaccusative verbs and auxiliary selection Master's Thesis Presented to The Faculty of the Graduate School of Arts and Sciences Brandeis University Department of Computer Science James Pustejovsky, Advisor In Partial Fulfillment of the Requirements for Master's Degree By Richard A. Brutti Jr. May 2012 c Copyright by Richard A. Brutti Jr. 2012 All Rights Reserved ABSTRACT To be or not to be: A corpus-based study of unaccusative verbs and auxiliary selection A thesis presented to the Department of Computer Science Graduate School of Arts and Sciences Brandeis University Waltham, Massachusetts Richard A. Brutti Jr. Since the introduction of the Unaccusative Hypothesis (Perlmutter, 1978), there have been many further attempts to explain the mechanisms behind the division in intransitive verbs. This paper aims to analyze and test some of theories of unac- cusativity using computational linguistic tools. Specifically, I focus on verbs that exhibit split intransitivity, that is, verbs that can appear in both unaccusative and unergative constructions, and in determining the distinguishing features that make this alternation possible. Many formal linguistic theories of unaccusativity involve the interplay of semantic roles and temporal event markers, both of which can be analyzed using statistical computational linguistic tools, including semantic role labelers, semantic parses, and automatic event classification. I use auxiliary verb selection as a surface-level indicator of unaccusativity in Italian and Dutch, and iii test various classes of verbs extracted from the Europarl corpus (Koehn, 2005). Additionally, I provide some historical background for the evolution of this dis- tinction, and analyze how my results fit into the larger theoretical framework. -
The Translation Equivalents Database (Treq) As a Lexicographer’S Aid
The Translation Equivalents Database (Treq) as a Lexicographer’s Aid Michal Škrabal, Martin Vavřín Institute of the Czech National Corpus, Charles University, Czech Republic E-mail: [email protected], [email protected] Abstract The aim of this paper is to introduce a tool that has recently been developed at the Institute of the Czech National Corpus, the Treq (Translation Equivalents) database, and to explore its possible uses, especially in the field of lexicography. Equivalent candidates offered by Treq can also be considered as potential equivalents in a bilingual dictionary (we will focus on the Latvian–Czech combination in this paper). Lexicographers instantly receive a list of candidates for target language counterparts and their frequencies (expressed both in absolute numbers and percentages) that suggest the probability that a given candidate is functionally equivalent. A significant advantage is the possibility to click on any one of these candidates and immediately verify their individual occurrences in a given context; and thus more easily distinguish the relevant translation candidates from the misleading ones. This utility, which is based on data stored in the InterCorp parallel corpus, is continually being upgraded and enriched with new functions (the recent integration of multi-word units, adding English as the primary language of the dictionaries, an improved interface, etc.), and the accuracy of the results is growing as the volume of data keeps increasing. Keywords: InterCorp; Treq; translation equivalents; alignment; Latvian–Czech dictionary 1. Introduction The aim of this paper is to introduce one of the tools that has been developed recently at the Institute of the Czech National Corpus (ICNC) and which could be especially helpful to lexicographers: namely, the Treq translation equivalents database1. -
The Pile: an 800GB Dataset of Diverse Text for Language Modeling Leo Gao Stella Biderman Sid Black Laurence Golding
The Pile: An 800GB Dataset of Diverse Text for Language Modeling Leo Gao Stella Biderman Sid Black Laurence Golding Travis Hoppe Charles Foster Jason Phang Horace He Anish Thite Noa Nabeshima Shawn Presser Connor Leahy EleutherAI [email protected] Abstract versity leads to better downstream generalization capability (Rosset, 2019). Additionally, large-scale Recent work has demonstrated that increased training dataset diversity improves general language models have been shown to effectively cross-domain knowledge and downstream gen- acquire knowledge in a novel domain with only eralization capability for large-scale language relatively small amounts of training data from that models. With this in mind, we present the domain (Rosset, 2019; Brown et al., 2020; Carlini Pile: an 825 GiB English text corpus tar- et al., 2020). These results suggest that by mix- geted at training large-scale language mod- ing together a large number of smaller, high qual- els. The Pile is constructed from 22 diverse ity, diverse datasets, we can improve the general high-quality subsets—both existing and newly cross-domain knowledge and downstream general- constructed—many of which derive from aca- demic or professional sources. Our evalua- ization capabilities of the model compared to mod- tion of the untuned performance of GPT-2 and els trained on only a handful of data sources. GPT-3 on the Pile shows that these models struggle on many of its components, such as To address this need, we introduce the Pile: a academic writing. Conversely, models trained 825:18 GiB English text dataset designed for train- on the Pile improve significantly over both ing large scale language models. -
Semantic Role Annotation of a French-English Corpus
Semantic Role Annotation of a French-English Corpus Lonneke van der Plas, James Henderson, Paola Merlo Distribution: Public CLASSiC Computational Learning in Adaptive Systems for Spoken Conversation 216594 Deliverable 6.2 Feb 2010 Project funded by the European Community under the Seventh Framework Programme for Research and Technological Development The deliverable identification sheet is to be found on the reverse of this page. Project ref. no. 216594 Project acronym CLASSiC Project full title Computational Learning in Adaptive Systems for Spoken Conversation Instrument STREP Thematic Priority Cognitive Systems, Interaction, and Robotics Start date / duration 01 March 2008 / 36 Months Security Public Contractual date of delivery M24 = March 2010 Actual date of delivery Feb 2010 Deliverable number 6.2 Deliverable title Semantic Role Annotation of a French-English Corpus Type Report Status & version Draft 1.0 Number of pages 53 (excluding front matter) Contributing WP 2 WP/Task responsible UNIGE Other contributors Author(s) Lonneke van der Plas, James Henderson, Paola Merlo EC Project Officer Philippe Gelin Keywords semantic role annotation corpus French English The partners in CLASSiC are: Heriot-Watt University HWU University of Cambridge UCAM University of Geneva GENE Ecole Superieure d’Electricite SUPELEC France Telecom/ Orange Labs FT University of Edinburgh HCRC EDIN For copies of reports, updates on project activities and other CLASSIC-related information, contact: The CLASSIC Project Co-ordinator: Dr. Oliver Lemon School of Mathematical and Computer Sciences (MACS) Heriot-Watt University Edinburgh EH14 4AS United Kingdom [email protected] Phone +44 (131) 451 3782 - Fax +44 (0)131 451 3327 Copies of reports and other material can also be accessed via the project’s administration homepage, http://www.classic-project.org c 2010, The Individual Authors. -
Standard Test Collection for English-Persian Cross-Lingual Word Sense Disambiguation
Standard Test Collection for English-Persian Cross-Lingual Word Sense Disambiguation Navid Rekabsaz, Serwah Sabetghadam, Mihai Lupu, Linda Andersson, Allan Hanbury Vienna University of Technology Favoritenstrasse 9 1040 Vienna Austria [email protected] Abstract In this paper, we address the shortage of evaluation benchmarks on Persian (Farsi) language by creating and making available a new benchmark for English to Persian Cross Lingual Word Sense Disambiguation (CL-WSD). In creating the benchmark, we follow the format of the SemEval 2013 CL-WSD task, such that the introduced tools of the task can also be applied on the benchmark. In fact, the new benchmark extends the SemEval-2013 CL-WSD task to Persian language. Keywords: Persian, Farsi, Cross Lingual Word Sense Disambiguation, test collection 1. Introduction 2. Resources in Persian Language Persian is a member of the Indo-European language fam- Word Sense Disambiguation (WSD)—the task of automat- ily, and uses Arabic letters for writing. Seraji et al. (2012) ically selecting the most related sense for a word occurring provide a comprehensive overview on the main characteris- in a context—is considered as a main step in the course tics of the language. For instance, the diacritic signs are not of approaching language understanding beyond the surface written—it is expected that the reader can read the text in of the words. WSD has been intensively studied in Natu- the absence of the short vowels. This characteristic causes ral Language Processing (NLP) (Navigli, 2012), Machine a special kind of word ambiguity in writing, such that some Translation (Chan et al., 2007; Costa-Jussa` and Farrus,´ words are pronounced differently while their written forms 2014), and Information Retrieval (Zhong and Ng, 2012). -
Actes Des 2Èmes Journées Scientifiques Du Groupement De Recherche Linguistique Informatique Formelle Et De Terrain (LIFT)
Actes des 2èmes journées scientifiques du Groupement de Recherche Linguistique Informatique Formelle et de Terrain (LIFT). Thierry Poibeau, Yannick Parmentier, Emmanuel Schang To cite this version: Thierry Poibeau, Yannick Parmentier, Emmanuel Schang. Actes des 2èmes journées scientifiques du Groupement de Recherche Linguistique Informatique Formelle et de Terrain (LIFT).. Poibeau, Thierry and Parmentier, Yannick and Schang, Emmanuel. Dec 2020, Montrouge, France. CNRS, 2020. hal-03066031 HAL Id: hal-03066031 https://hal.archives-ouvertes.fr/hal-03066031 Submitted on 3 Jan 2021 HAL is a multi-disciplinary open access L’archive ouverte pluridisciplinaire HAL, est archive for the deposit and dissemination of sci- destinée au dépôt et à la diffusion de documents entific research documents, whether they are pub- scientifiques de niveau recherche, publiés ou non, lished or not. The documents may come from émanant des établissements d’enseignement et de teaching and research institutions in France or recherche français ou étrangers, des laboratoires abroad, or from public or private research centers. publics ou privés. LIFT 2020 Actes des 2èmes journées scientifiques du Groupement de Recherche Linguistique Informatique Formelle et de Terrain (LIFT) Thierry Poibeau, Yannick Parmentier, Emmanuel Schang (Éds.) 10-11 décembre 2020 Montrouge, France (Virtuel) Comités Comité d’organisation Thierry Poibeau, LATTICE/CNRS Yannick Parmentier, LORIA/Université de Lorraine Emmanuel Schang, LLL/Université d’Orléans Comité de programme Angélique Amelot LPP/CNRS -
Projecto Em Engenharia Informatica
UNIVERSIDADE DE LISBOA Faculdade de Cienciasˆ Departamento de Informatica´ SPEECH-TO-SPEECH TRANSLATION TO SUPPORT MEDICAL INTERVIEWS Joao˜ Antonio´ Santos Gomes Rodrigues PROJETO MESTRADO EM ENGENHARIA INFORMATICA´ Especializac¸ao˜ em Interacc¸ao˜ e Conhecimento 2013 UNIVERSIDADE DE LISBOA Faculdade de Cienciasˆ Departamento de Informatica´ SPEECH-TO-SPEECH TRANSLATION TO SUPPORT MEDICAL INTERVIEWS Joao˜ Antonio´ Santos Gomes Rodrigues PROJETO MESTRADO EM ENGENHARIA INFORMATICA´ Especializac¸ao˜ em Interacc¸ao˜ e Conhecimento Projeto orientado pelo Prof. Doutor Antonio´ Manuel Horta Branco 2013 Agradecimentos Agradec¸o ao meu orientador, Antonio´ Horta Branco, por conceder a oportunidade de realizar este trabalho e pela sua sagacidade e instruc¸ao˜ oferecida para a concretizac¸ao˜ do mesmo. Agradec¸o aos meus parceiros do grupo NLX, por terem aberto os caminhos e cri- ado inumeras´ ferramentas e conhecimento para o processamento de linguagem natural do portugues,ˆ das quais fac¸o uso neste trabalho. Assim como pela imprescind´ıvel partilha e companhia. Agradec¸o a` minha fam´ılia e a` Joana, pelo apoio inefavel.´ Este trabalho foi apoiado pela Comissao˜ Europeia no ambitoˆ do projeto METANET4U (ECICTPSP:270893), pela Agenciaˆ de Inovac¸ao˜ no ambitoˆ do projeto S4S (S4S / PLN) e pela Fundac¸ao˜ para a Cienciaˆ e Tecnologia no ambitoˆ do projeto DP4LT (PTDC / EEISII / 1940 / 2012). As` tresˆ expresso a minha sincera gratidao.˜ iii Resumo Este relatorio´ apresenta a criac¸ao˜ de um sistema de traduc¸ao˜ fala-para-fala. O sistema consiste na captac¸ao˜ de voz na forma de sinal audio´ que de seguida e´ interpretado, tra- duzido e sintetizado para voz. Tendo como entrada um enunciado numa linguagem de origem e como sa´ıda um enunciado numa linguagem destino. -
New Kazakh Parallel Text Corpora with On-Line Access
New Kazakh parallel text corpora with on-line access Zhandos Zhumanov1, Aigerim Madiyeva2 and Diana Rakhimova3 al-Farabi Kazakh National University, Laboratory of Intelligent Information Systems, Almaty, Kazakhstan [email protected], [email protected], [email protected] Abstract. This paper presents a new parallel resource – text corpora – for Ka- zakh language with on-line access. We describe 3 different approaches to col- lecting parallel text and how much data we managed to collect using them, par- allel Kazakh-English text corpora collected from various sources and aligned on sentence level, and web accessible corpus management system that was set up using open source tools – corpus manager Mantee and web GUI KonText. As a result of our work we present working web-accessible corpus management sys- tem to work with collected corpora. Keywords: parallel text corpora, Kazakh language, corpus management system 1 Introduction Linguistic text corpora are large collections of text used for different language studies. They are used in linguistics and other fields that deal with language studies as an ob- ject of study or as a resource. Text corpora are needed for almost any language study since they are basically a representation of the language itself. In computer linguistics text corpora are used for various parsing, machine translation, speech recognition, etc. As shown in [1] text corpora can be classified by many categories: Size: small (to 1 million words); medium (from 1 to 10 million words); large (more than 10 million words). Number of Text Languages: monolingual, bilingual, multilingual. Language of Texts: English, German, Ukrainian, etc. Mode: spoken; written; mixed.